rjroy

Use when checking whether field-guide reference pages still match current code and tests. Reads pages plus fg-evidence anchors, reports or fixes semantic drift, and can use sub-agents for parallel audit batches. Triggers include "resolve drift", "semantic drift", "check accuracy", "verify the reference against code", and "audit the wiki".

Use after ingesting or editing field-guide pages to attach living code/test anchors. Adds or refreshes fg-evidence metadata without trying to prove prose accuracy. Triggers include "update evidence", "wire evidence", "add evidence anchors", and "connect the wiki to code".

Use when extracting knowledge from .lore/ artifacts into the reference wiki. Converts work artifacts (retros, specs, plans, research, notes) into structured wiki pages grouped by knowledge type. Reads Markdown or HTML sources and writes Markdown by default. Triggers include "ingest this", "extract knowledge from", "add this to the wiki", "update the reference from", and "populate the field guide".

Use when setting up field-guide on a project for the first time, or to refresh the scheduled lint job after it expires. Triggers include "init field-guide", "set up field-guide", "refresh field-guide lint schedule", and "bootstrap the wiki".

This skill is used when the project wiki needs a health check. Triggers include 'lint the wiki', 'check wiki health', 'run field-guide lint', 'are there stale wiki pages', 'find orphaned pages', 'check for contradictions in the wiki'.

Use when asking questions about the project wiki, querying accumulated knowledge, searching project decisions or lessons. Triggers include "query the wiki", "what does the wiki say about", "search project knowledge", and natural language questions directed at the field-guide wiki.

Use when exploring before committing, thinking through trade-offs, or digesting sketches and diagrams. Triggers include "let's brainstorm", "what if we...", and "explore options". Bad ideas welcome, questions over answers, mistakes on purpose.

Use to add validation criteria to a spec or plan. Triggers include "define validation", "how will we validate", "what should the AI check", and "add validation to this".

This skill should be used when the GM needs to create Apocrypha adversaries, build adversary keyword blocks, design Fear abilities, determine stress thresholds, set adversary tier and difficulty, track adversary stress during encounters, or reference adversary templates and examples for minor, standard, and major tier adversaries.

This skill should be used when the GM needs to handle Apocrypha combat situations, including resolving attacks against adversaries, dealing stress to adversaries, tracking adversary stress and defeat, spending Fear in combat, activating adversary Fear abilities, managing encounter state, or running player-rolls-everything combat encounters.

This skill should be used when the GM needs to help players create Apocrypha characters, define keywords with scoping and exclusions, handle character advancement and level-up, manage keyword splitting or retirement, track progression milestones, set up rest and recovery scenes, or reference character sheet and story templates.

This skill should be used when the GM needs to look up Apocrypha rules, check how a mechanic works, verify dice resolution, understand the hope/fear economy, reference stress rules, check keyword scoping, look up rest and recovery, understand progression and leveling, review session and act structure, or get GM guidelines for running Apocrypha.

This skill should be used when the GM needs storytelling techniques, handling player failure, NPC creation, scene pacing, or improv principles. Triggers on "fail forward", "succeed at cost", "yes and", "how do you want to do this", "NPC motivation", "scene transitions", "player agency".

This skill should be used when the GM needs to handle combat situations, including starting combat, rolling initiative, resolving attack rolls, managing combat encounters, rolling damage, tracking hit points, applying conditions, or running d20-style tactical combat. Provides combat flow, turn structure, attack resolution, and condition references.

This skill should be used when the GM needs to handle spellcasting situations, including resolving spell effects, managing spell slots, calculating spell save DCs, handling concentration, resolving spell attacks, determining spellcasting abilities, handling cantrips, or processing ritual casting. Provides spellcasting rules, formulas, and references for running magical gameplay.

This skill should be used when the GM needs to create NPCs or monsters, generate stat blocks, determine enemy stats, design creatures, or generate adversaries for d20-style RPG encounters. Provides SRD 5.2 stat block format and NPC templates.

Reorganizes a flat directory of reference documents into layered subdirectories that support progressive discovery. Use when a single directory has accumulated enough docs that "all in one place" is hindering navigation rather than helping it, when readers can't tell where to start, or when the user explicitly asks to "stratify", "layer", "rearrange for progressive discovery", or "split this directory into categories". Triggers include phrases like "too many files in one directory", "no clear entry point", "hard to find the why", "where do I start reading".

Consult the guild's craft knowledge compendium for reference material relevant to the current task. Use when starting a code review, writing a spec, writing a plan, making design decisions, conducting research, beginning implementation from a plan, writing a commission prompt, working with TypeScript patterns, generating images, designing visual assets, conducting strategic analysis, setting up a new project's architecture, designing a CSS color system, building with the Claude Agent SDK, or entering any domain the compendium covers. Triggers include "check the compendium", "consult reference", "craft guidance", "reference entries".

Propose a new compendium entry when you notice a knowledge gap during work. Use when the compendium doesn't cover a domain you need, when a topic would benefit from a reference entry, when you encounter a recurring pattern that should be documented, or when no compendium entry exists for a topic you're working in. Triggers include "compendium gap", "propose entry", "needs a reference entry", "compendium doesn't cover this".

Review completed commission artifacts as a batch, extract loose threads into a retro, and delete the commission files. Use after a feature's implement-review-fix cycle completes, before creating a PR, or when .lore/work/commissions/ (or the flat-layout .lore/commissions/) has accumulated files that no longer represent active work. Triggers include "clean up commissions", "commission cleanup", "review commissions", "batch cleanup".

Review completed meeting artifacts as a batch, extract untracked decisions into a retro, update memory, and delete the meeting files. Use when .lore/work/meetings/ (or the flat-layout .lore/meetings/) has accumulated closed meetings, after a feature push with multiple meetings, or periodically to keep the directory current. Triggers include "clean up meetings", "meeting cleanup", "review meetings".

This skill should be used when the user says "/daily-prep", "daily prep", "morning prep", "what should I focus on today", "plan my day", "start my day", "prep for today", or wants help deciding what to work on. Creates a morning commitment with energy and calendar context.

This skill should be used when the user says "research mode", "/research", "help me think through", "what do I know about", "based on my notes", "what have I written about", "let's talk about", mentions timeframes like "this week" or "last month", references people or projects by name, or when the conversation naturally benefits from proactive vault context.

This skill should be used when the user asks to "find tasks", "show tasks", "list tasks", "query tasks", "tasks with status", "fire tasks", "incomplete tasks", "tasks in inbox", "tasks in projects", or mentions task checkboxes with status markers (x, f, /, b, ?). Provides task querying across PARA directories in Obsidian vaults.

Use this skill when the user asks about analyzing audio files for musical characteristics like tempo, key, beats, structure, or when comparing two audio files. Triggers on questions about BPM detection, key/mode detection, beat tracking, song structure analysis, chromagram analysis, spectrogram generation, harmonic-percussive separation, or audio file similarity.

Use this skill when the user asks about analyzing MIDI files for musical characteristics like key, chords, melody patterns, rhythm, structure, or composition metrics. Triggers on questions about MIDI key detection, chord progressions, Roman numeral analysis, melodic motifs, rhythmic patterns, time signatures, song form (A-B-A), or composition complexity metrics.

Analyzes MIDI files to extract melodic motifs, rhythmic patterns, and phrase structures for lyric writing. This skill should be used when the user wants to write lyrics that match the phrasing of an existing MIDI file, or when analyzing a song's melodic structure to understand its "lyrical shape." Triggers on requests like "analyze this MIDI for lyrics", "what's the phrasing in this song", or "help me write lyrics to match this melody."

This skill should be used when the user asks to "find tasks", "show tasks", "list tasks", "query tasks", "tasks with status", "fire tasks", "incomplete tasks", "tasks in inbox", "tasks in projects", or mentions task checkboxes with status markers (x, f, /, b, ?). Provides task querying across PARA directories in Obsidian vaults.

Run typecheck, lint, and tests to verify the codebase is healthy. Use after making changes or before committing.